Patentable/Patents/US-6249781
US-6249781

Method and apparatus for machine learning

PublishedJune 19, 2001
Assigneenot available in USPTO data we have
Inventorsnot available in USPTO data we have
Technical Abstract

A method and apparatus is disclosed for machine learning of a pattern sequence which is derived from a plurality of inputs. The pattern sequence is predicted from learning rate parameters that are exponentially related to an incrementally calculated gain parameter for each input. The gain parameter are increased or decreased in real time in correlation with the accuracy of the learning process. The disclosed method and apparatus are advantageously utilized in signal processing, adaptive control systems, and pattern recognition.

Patent Claims
5 claims

Legal claims defining the scope of protection, as filed with the USPTO.

1

1. A computer system for determining a time dependent pattern sequence y(t), comprising: a memory configured to store instructions; and a processor configured to execute the instructions to receive a plurality of time dependent inputs x.sub.i (t) and a meta-step-size parameter .theta., determine a predicted value of the pattern sequence y(t) from the time dependent inputs based on a learning rate .alpha..sub.i that is exponentially related to an incremental gain .beta..sub.i (t), the incremental gain .beta..sub.i (t) being derived from previous values of .beta..sub.i (t), store the predicted value of the pattern sequence y(t) in the memory, and determine the pattern sequence y(t) using the stored predicted value.

2

2. The computer system of claim 1, wherein the predicted value of the pattern sequence is calculated as a linear combination of the plurality of time dependent inputs.

3

3. The computer system of claim 1, wherein the derivation means derives the incremental gain .beta..sub.i (t) according to the rule: EQU .beta..sub.i (t+1)=.beta..sub.i (t)+.theta..delta.(t)x.sub.i (t)h.sub.i (t), where .theta. is a positive constant denoted as the meta-learning rate, and h.sub.i is an additional per-input memory parameter updated by ##EQU5## where [x].sup.+ is defined as x for x>0, else 0.

4

4. The computer system of claim 1, wherein the predicted value of the pattern sequence is calculated as a non-linear combination of the plurality of time dependent inputs.

5

5. The computer system of claim 1, wherein the derivation means derives the incremental gain .beta..sub.i (t) according to the rule: EQU .beta..sub.i (t+1)=.beta..sub.i (t)+.theta..

Classification Codes (CPC)

Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.

Patent Metadata

Filing Date

May 5, 1999

Publication Date

June 19, 2001

Want to explore more patents?

Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.

Citation & reuse

Analysis on this page is generated by Patentable — an AI-powered patent intelligence platform. AI-generated summaries, explanations, and analysis may be reused with attribution and a visible link back to the canonical URL below. Patent abstracts and claims are USPTO public domain.

Cite as: Patentable. “Method and apparatus for machine learning” (US-6249781). https://patentable.app/patents/US-6249781

© 2026 Patentable. All rights reserved.

Patentable is a research and drafting-assistant tool, not a law firm, and does not provide legal advice. Documents we generate are drafts for review by a licensed patent attorney.